An AI agent is software that carries out an instruction rather than just answering it. You describe what you want, the agent plans the steps, uses the tools you make available, and delivers a result for you to review. This explanation is deliberately jargon-free: no 'LLM orchestration,' no 'tool calling,' just what an agent does, how it works, and when it can be useful to your business.
An AI agent is a program that pursues a goal through several steps. A language model provides its reasoning; the surrounding components let the program observe, decide, and act: access to files and systems, memory for earlier decisions, and rules about what it can and cannot do. Together, those components turn a conversational tool into something that can carry out work.
We use AI agents in the plural because, in practice, several often run alongside each other. One agent monitors your quote workflow, another prepares the weekly report, and another keeps an eye on Search Console. Each agent has its own task, permissions, and boundaries, so you decide what is allowed for each job. Gartner predicts that 33 percent of enterprise software applications will include agentic AI by 2028, up from less than 1 percent in 2024. Major vendors describe it in similar terms: an agent is a program that independently collects data, makes decisions, and carries out tasks, as ServiceNow explains.
In one sentence: AI agents are digital workers that accept an instruction, work through it independently, and present the result for review. See how Voltti puts that into practice on our page about AI agents for businesses.
An agent works in a cycle that repeats until the task is complete. First, it interprets the instruction and plans the steps. Then it carries out one step at a time with the available tools: reading a file, running a script, or querying an integration. After each step, it checks the result and decides whether to continue, adjust, or try again. It then delivers the result for review; its own checks do not guarantee that everything is correct.
Here is an example from our own work, from instruction to completed task. Our own Hermes installation at Voltti was asked to compile a prioritized list of articles that needed revision. Using its own read-only access, the agent read our Search Console data, calculated impressions and positions for each article, weighed those against how current the content was, and turned the list into concrete tasks. It recorded each step in a log. Search Console access is read-only; CMS access is separate. The agent edits directly in Storyblok and sometimes publishes the work itself, after which we review it and make corrections where needed. One task on that list was this article.
That cycle of planning, acting, checking, and adjusting also explains why an agent does more than a basic question-and-answer chatbot, which stops at the answer.
A basic chatbot without action tools returns text and waits for your next question. An AI agent can then get to work: it reads, writes, runs scripts, and delivers something ready for review. An agent can retain context and earlier decisions when memory is configured. Some chat products offer tools and memory too, so the distinction depends on the setup, not just the product name.
For a closer comparison, our article on AI agents versus chatbots covers the differences, costs, and a decision table. This table summarizes a basic chatbot without action tools or persistent memory versus an agent configured with those capabilities:
| Feature | Chatbot | AI agent |
|---|---|---|
Type of interaction | Text in, text out | Instruction in, result out |
File access | None in this basic setup | Yes, within agreed projects |
Memory | Within one session in this setup | Retains decisions and context when configured |
Using tools | Limited or none in this setup | Scripts, web search, integrations |
Human review | Review answers before using them | Yes, with approval for high-risk actions |
Where it works | In the chat window | Through your platforms: Telegram, Slack, desktop |
Tasks agents carry out in businesses today include reading, summarizing, and editing files; running scripts and checking the results; finding information in projects and knowledge bases; drafting or editing emails and quotes; analyzing data and generating reports; and preparing or completing recurring workflows.
The best starting point is not automating everything at once, but choosing one task that comes back every week. For more on selecting suitable processes, read about automating business processes with AI.
Not every AI agent is equally suited to business tasks. Five factors matter: open source, so you are not locked into one vendor; installation on your own infrastructure, so the environment runs at your business; tool use, so the agent can work with your existing software; memory, so it retains business context; and support, so someone handles updates, backups, and assistance.
We work with Hermes Agent, an open-source AI agent from Nous Research that supports this approach, with installation and support from Voltti. It works across multiple platforms your team already uses. For a practical look at the setup, see Hermes Agent explained; for the cost of your own environment, see our article on AI agent costs.
The biggest obstacle is not the technology, but deciding where to start. Our advice: start with one recurring task that takes time and causes frustration every week, rather than a strategic plan. Run a pilot around it: a short cycle, one task, and one person responsible for reviewing the result. The full process is described in Voltti's pilot approach.
Voltti installs and supports AI agents for businesses in Belgium and the Netherlands, from the first pilot to everyday use. Wondering whether your recurring task is a good starting point? Use the button below to discuss your pilot and choose a useful first task with us.
For a first-line support example, see what an AI agent can do in customer service.
Not exactly. ChatGPT combines a chat interface with tools and agent features, depending on your plan and settings. An AI agent such as Hermes can carry out tasks with the right access: reading files, running scripts, and working within your projects. Compare the enabled capabilities and permissions, not just the names.
No. If you work on your own, you can use Hermes Desktop on your workstation, with the agent's tools in an app. A team can work with the agent through platforms it already uses, such as Telegram, Slack, or Discord. The technical setup stays behind the scenes, with support from Voltti.
The environment runs on a system at your business. Access is limited to selected employees, and the agent gets the minimum permissions needed for each task, with read-only access wherever possible. Encrypted backups go to a separate location on your own network. Read more about our approach to security and privacy.
Yes, and we recommend it. Start with one person using Hermes Desktop on a workstation and one workflow. As more people join, the team can use a channel it already works with, such as Buzz, Telegram, Slack, or Discord. There is no required channel migration. Expanding a working setup is usually easier than setting it up for the first time.
That depends on what you want to automate and where the environment runs. Voltti therefore always provides a custom quote, without a standard monthly rate. To see what determines that quote, read our article on AI agent costs.
